Re:Mistral now trains on user input by default, except on en...
by Zambyte on Wednesday September 02, 2026 @01:55PM
(#49539930)
Thanks for the pointer! I had set up mistral a while back using pi to compliment my local Qwen usage, but I found Qwen to just be better for all of my tasks at a substantially cheaper price, and reasonably fast tps. I also tried signing up for z.ai, but they would never send me an email to sign in. Using GLM through mistral to compliment my local models seems like exactly what I want.
[ Parent
| on HN ]
Re:Mistral now trains on user input by default, except on en...
by evanjrowley on Sunday September 06, 2026 @10:38AM
(#49586932)
Qwen is leaving a strong impression on me as well. Qwen-3.8-Max via openrouter has been a strong performer for me. I run it in autolith and then have claude code check the commits. Claude highly praises the quality of the work. Lol